Merge pull request #6041 from meilisearch/fix-workflow-injection

Remove risk of command injection

.github/workflows/sdks-tests.yml

@@ -25,14 +25,18 @@ jobs:
       - uses: actions/checkout@v5
       - name: Define the Docker image we need to use
         id: define-image
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          DOCKER_IMAGE_INPUT: ${{ github.event.inputs.docker_image }}
         run: |
-          event=${{ github.event_name }}
           echo "docker-image=nightly" >> $GITHUB_OUTPUT
-          if [[ $event == 'workflow_dispatch' ]]; then
+          if [[ "$EVENT_NAME" == 'workflow_dispatch' ]]; then
-            echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
+            echo "docker-image=$DOCKER_IMAGE_INPUT" >> $GITHUB_OUTPUT
           fi
       - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
+        env:
+          DOCKER_IMAGE: ${{ steps.define-image.outputs.docker-image }}
+        run: echo "Docker image is $DOCKER_IMAGE"
 
 ##########
 ## SDKs ##

crates/index-scheduler/src/queue/batches.rs

@@ -502,11 +502,13 @@ impl Queue {
             *before_finished_at,
         )?;
 
+        if let Some(limit) = limit {
             batches = if query.reverse.unwrap_or_default() {
-            batches.into_iter().take(*limit).collect()
+                batches.into_iter().take(*limit as usize).collect()
             } else {
-            batches.into_iter().rev().take(*limit).collect()
+                batches.into_iter().rev().take(*limit as usize).collect()
             };
+        }
 
         Ok(batches)
     }
@@ -600,8 +602,11 @@ impl Queue {
             Box::new(batches.into_iter().rev()) as Box<dyn Iterator<Item = u32>>
         };
 
-        let batches =
+        let batches = self.batches.get_existing_batches(
-            self.batches.get_existing_batches(rtxn, batches.take(query.limit), processing)?;
+            rtxn,
+            batches.take(query.limit.unwrap_or(u32::MAX) as usize),
+            processing,
+        )?;
 
         Ok((batches, total))
     }

crates/index-scheduler/src/queue/batches_test.rs

@@ -28,21 +28,21 @@ fn query_batches_from_and_limit() {
 
     let proc = index_scheduler.processing_tasks.read().unwrap().clone();
     let rtxn = index_scheduler.env.read_txn().unwrap();
-    let query = Query { limit: 0, ..Default::default() };
+    let query = Query { limit: Some(0), ..Default::default() };
     let (batches, _) = index_scheduler
         .queue
         .get_batch_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &proc)
         .unwrap();
     snapshot!(snapshot_bitmap(&batches), @"[]");
 
-    let query = Query { limit: 1, ..Default::default() };
+    let query = Query { limit: Some(1), ..Default::default() };
     let (batches, _) = index_scheduler
         .queue
         .get_batch_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &proc)
         .unwrap();
     snapshot!(snapshot_bitmap(&batches), @"[2,]");
 
-    let query = Query { limit: 2, ..Default::default() };
+    let query = Query { limit: Some(2), ..Default::default() };
     let (batches, _) = index_scheduler
         .queue
         .get_batch_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &proc)
@@ -63,14 +63,14 @@ fn query_batches_from_and_limit() {
         .unwrap();
     snapshot!(snapshot_bitmap(&batches), @"[0,1,2,]");
 
-    let query = Query { from: Some(1), limit: 1, ..Default::default() };
+    let query = Query { from: Some(1), limit: Some(1), ..Default::default() };
     let (batches, _) = index_scheduler
         .queue
         .get_batch_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &proc)
         .unwrap();
     snapshot!(snapshot_bitmap(&batches), @"[1,]");
 
-    let query = Query { from: Some(1), limit: 2, ..Default::default() };
+    let query = Query { from: Some(1), limit: Some(2), ..Default::default() };
     let (batches, _) = index_scheduler
         .queue
         .get_batch_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &proc)

crates/index-scheduler/src/queue/mod.rs

@@ -31,9 +31,6 @@ use crate::{Error, IndexSchedulerOptions, Result, TaskId};
 
 /// The number of database used by queue itself
 const NUMBER_OF_DATABASES: u32 = 1;
-/// The default limit for pagination
-const DEFAULT_LIMIT: usize = 20;
-
 /// Database const names for the `IndexScheduler`.
 mod db_name {
     pub const BATCH_TO_TASKS_MAPPING: &str = "batch-to-tasks-mapping";
@@ -43,11 +40,11 @@ mod db_name {
 ///
 /// An empty/default query (where each field is set to `None`) matches all tasks.
 /// Each non-null field restricts the set of tasks further.
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Default, Debug, Clone, PartialEq, Eq)]
 pub struct Query {
-    /// The maximum number of tasks to be matched. Defaults to 20.
+    /// The maximum number of tasks to be matched
-    pub limit: usize,
+    pub limit: Option<u32>,
-    /// The minimum [task id](`meilisearch_types::tasks::Task::uid`) to be matched. Defaults to 0.
+    /// The minimum [task id](`meilisearch_types::tasks::Task::uid`) to be matched
     pub from: Option<u32>,
     /// The order used to return the tasks. By default the newest tasks are returned first and the boolean is `false`.
     pub reverse: Option<bool>,
@@ -86,29 +83,32 @@ pub struct Query {
     pub after_finished_at: Option<OffsetDateTime>,
 }
 
-impl Default for Query {
+impl Query {
-    fn default() -> Self {
+    /// Return `true` if every field of the query is set to `None`, such that the query
-        Self {
+    /// matches all tasks.
-            limit: DEFAULT_LIMIT,
+    pub fn is_empty(&self) -> bool {
-            from: Default::default(),
+        matches!(
-            reverse: Default::default(),
+            self,
-            uids: Default::default(),
+            Query {
-            batch_uids: Default::default(),
+                limit: None,
-            statuses: Default::default(),
+                from: None,
-            types: Default::default(),
+                reverse: None,
-            index_uids: Default::default(),
+                uids: None,
-            canceled_by: Default::default(),
+                batch_uids: None,
-            before_enqueued_at: Default::default(),
+                statuses: None,
-            after_enqueued_at: Default::default(),
+                types: None,
-            before_started_at: Default::default(),
+                index_uids: None,
-            after_started_at: Default::default(),
+                canceled_by: None,
-            before_finished_at: Default::default(),
+                before_enqueued_at: None,
-            after_finished_at: Default::default(),
+                after_enqueued_at: None,
-        }
+                before_started_at: None,
+                after_started_at: None,
+                before_finished_at: None,
+                after_finished_at: None,
             }
+        )
     }
 
-impl Query {
     /// Add an [index id](meilisearch_types::tasks::Task::index_uid) to the list of permitted indexes.
     pub fn with_index(self, index_uid: String) -> Self {
         let mut index_vec = self.index_uids.unwrap_or_default();
@@ -119,7 +119,7 @@ impl Query {
     // Removes the `from` and `limit` restrictions from the query.
     // Useful to get the total number of tasks matching a filter.
     pub fn without_limits(self) -> Self {
-        Query { limit: usize::MAX, from: None, ..self }
+        Query { limit: None, from: None, ..self }
     }
 }
 

crates/index-scheduler/src/queue/tasks.rs

@@ -465,11 +465,13 @@ impl Queue {
             *before_finished_at,
         )?;
 
+        if let Some(limit) = limit {
             tasks = if query.reverse.unwrap_or_default() {
-            tasks.into_iter().take(*limit).collect()
+                tasks.into_iter().take(*limit as usize).collect()
             } else {
-            tasks.into_iter().rev().take(*limit).collect()
+                tasks.into_iter().rev().take(*limit as usize).collect()
             };
+        }
 
         Ok(tasks)
     }
@@ -527,7 +529,9 @@ impl Queue {
         } else {
             Box::new(tasks.into_iter().rev()) as Box<dyn Iterator<Item = u32>>
         };
-        let tasks = self.tasks.get_existing_tasks(rtxn, tasks.take(query.limit))?;
+        let tasks = self
+            .tasks
+            .get_existing_tasks(rtxn, tasks.take(query.limit.unwrap_or(u32::MAX) as usize))?;
 
         let ProcessingTasks { batch, processing, progress: _ } = processing_tasks;
 

crates/index-scheduler/src/queue/tasks_test.rs

@@ -28,21 +28,21 @@ fn query_tasks_from_and_limit() {
 
     let rtxn = index_scheduler.env.read_txn().unwrap();
     let processing = index_scheduler.processing_tasks.read().unwrap();
-    let query = Query { limit: 0, ..Default::default() };
+    let query = Query { limit: Some(0), ..Default::default() };
     let (tasks, _) = index_scheduler
         .queue
         .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &processing)
         .unwrap();
     snapshot!(snapshot_bitmap(&tasks), @"[]");
 
-    let query = Query { limit: 1, ..Default::default() };
+    let query = Query { limit: Some(1), ..Default::default() };
     let (tasks, _) = index_scheduler
         .queue
         .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &processing)
         .unwrap();
     snapshot!(snapshot_bitmap(&tasks), @"[2,]");
 
-    let query = Query { limit: 2, ..Default::default() };
+    let query = Query { limit: Some(2), ..Default::default() };
     let (tasks, _) = index_scheduler
         .queue
         .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &processing)
@@ -63,14 +63,14 @@ fn query_tasks_from_and_limit() {
         .unwrap();
     snapshot!(snapshot_bitmap(&tasks), @"[0,1,2,]");
 
-    let query = Query { from: Some(1), limit: 1, ..Default::default() };
+    let query = Query { from: Some(1), limit: Some(1), ..Default::default() };
     let (tasks, _) = index_scheduler
         .queue
         .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &processing)
         .unwrap();
     snapshot!(snapshot_bitmap(&tasks), @"[1,]");
 
-    let query = Query { from: Some(1), limit: 2, ..Default::default() };
+    let query = Query { from: Some(1), limit: Some(2), ..Default::default() };
     let (tasks, _) = index_scheduler
         .queue
         .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default(), &processing)

crates/meilisearch/src/routes/metrics.rs

@@ -185,7 +185,7 @@ pub async fn get_metrics(
         // Fetch the finished batches...
         &Query {
             statuses: Some(vec![Status::Succeeded, Status::Failed]),
-            limit: 1,
+            limit: Some(1),
             ..Query::default()
         },
         auth_filters,
@@ -214,7 +214,7 @@ pub async fn get_metrics(
     let task_queue_latency_seconds = index_scheduler
         .get_tasks_from_authorized_indexes(
             &Query {
-                limit: 1,
+                limit: Some(1),
                 reverse: Some(true),
                 statuses: Some(vec![Status::Enqueued, Status::Processing]),
                 ..Query::default()

crates/meilisearch/src/routes/tasks.rs

@@ -126,7 +126,7 @@ pub struct TasksFilterQuery {
 impl TasksFilterQuery {
     pub(crate) fn into_query(self) -> Query {
         Query {
-            limit: self.limit.0 as usize,
+            limit: Some(self.limit.0),
             from: self.from.as_deref().copied(),
             reverse: self.reverse.as_deref().copied(),
             batch_uids: self.batch_uids.merge_star_and_none(),
@@ -225,8 +225,7 @@ pub struct TaskDeletionOrCancelationQuery {
 impl TaskDeletionOrCancelationQuery {
     fn into_query(self) -> Query {
         Query {
-            // We want to delete all tasks that match the given filters
+            limit: None,
-            limit: usize::MAX,
             from: None,
             reverse: None,
             batch_uids: self.batch_uids.merge_star_and_none(),